Add ogc.osc.prov-processing-step: PROV profile for a single geospatial processing step

.gitignore

@@ -3,3 +3,4 @@ build-local/
 bblocks-config-local.yml
 bblocks-config-local.yaml
 .volumes
+*.bak

README.md

@@ -1,3 +1,4 @@
+Note: see issue #11 — EarthCODE example URLs currently 404 and block the register build.
 # Open Science Building Blocks 
 
 The repository documents a set of [OGC Building Blocks](https:blocks.ogc.org). for Open Science, which in turn leverage reusable ontologies, schemas, APIs etc. from published OGC standards.

_sources/prov-processing-step/bblock.json

@@ -0,0 +1,13 @@
+{
+  "name": "Geospatial Processing Step Provenance",
+  "abstract": "A profile of the PROV-O building block constrained to the description of a single geospatial processing step, with a required link to a registered process type.",
+  "status": "under-development",
+  "dateTimeAddition": "2026-08-05T00:00:00Z",
+  "itemClass": "schema",
+  "version": "0.1.0",
+  "dateOfLastChange": "2026-08-05",
+  "maturity": "development",
+  "scope": "unstable",
+  "tags": ["provenance", "prov-o", "processing", "ospd"],
+  "dependsOn": ["ogc.ogc-utils.prov"]
+}

_sources/prov-processing-step/description.md

@@ -0,0 +1,20 @@
+# Geospatial Processing Step Provenance
+
+This building block profiles `ogc-utils.prov` down to a single unit: one
+geospatial processing step.
+
+PROV-O is deliberately general. Any valid PROV document is a valid description
+of a processing step, which makes validation weak and cross-platform comparison
+hard.
+
+OGC API - Processes Part 5 (draft 26-038) narrows this for job provenance: a
+job entity, a process entity, an activity joining them, and input/output
+artifacts carrying roles. This profile follows that shape.
+
+Part 5 does not define any link from a process to a registered process type.
+This profile makes that link required, via the processType property. It is the
+point at which the OSPD 2026 profile-plus-register pattern closes: the profile
+gives the structure, the register gives the controlled term.
+
+Under development as part of OSPD 2026, deliverable D104 (Aganitha Space
+Technologies, Workflow Profiler).

_sources/prov-processing-step/examples.yaml

@@ -0,0 +1,45 @@
+- title: Reprojection of a gridded precipitation dataset
+  description: >-
+    A single reprojection step, transforming a gridded precipitation dataset
+    from a geographic CRS to a projected CRS. Reprojection was the one
+    operation common to every workflow presented at the OSPD 2026 kick-off,
+    which makes it the natural first candidate for the process-type register.
+  snippets:
+    - language: json
+      code: |
+        {
+          "id": "urn:aganitha:step:reproject:20260805T101500Z",
+          "provType": "Activity",
+          "processType": "https://example.org/ospd/process-types/reprojection",
+          "label": "Reproject precipitation grid to national projected CRS",
+          "startedAtTime": "2026-08-05T10:15:00Z",
+          "endedAtTime": "2026-08-05T10:15:42Z",
+          "used": ["urn:aganitha:dataset:precip-daily-geographic"],
+          "generated": ["urn:aganitha:dataset:precip-daily-projected"],
+          "qualifiedUsage": [
+            {
+              "entity": "urn:aganitha:dataset:precip-daily-geographic",
+              "hadRole": "https://example.org/ospd/roles/sourceGrid"
+            }
+          ],
+          "wasAssociatedWith": ["https://gdal.org/"],
+          "parameters": {
+            "sourceCrs": "EPSG:4326",
+            "targetCrs": "EPSG:7755",
+            "resamplingMethod": "bilinear"
+          }
+        }
+
+- title: Minimal conforming step
+  description: >-
+    The smallest document that satisfies this profile.
+  snippets:
+    - language: json
+      code: |
+        {
+          "id": "urn:example:step:0001",
+          "provType": "Activity",
+          "processType": "https://example.org/ospd/process-types/reprojection",
+          "used": ["urn:example:input:0001"],
+          "generated": ["urn:example:output:0001"]
+        }

_sources/prov-processing-step/schema.yaml

@@ -0,0 +1,82 @@
+$schema: https://json-schema.org/draft/2020-12/schema
+title: Geospatial Processing Step Provenance
+description: >-
+  A single geospatial processing step, expressed as a constrained profile of
+  PROV-O. Inputs and outputs are entity references; the role each played is
+  expressed through prov:qualifiedUsage rather than inline, so the profile
+  stays compatible with the PROV-O object model.
+
+allOf:
+  - $ref: bblocks://ogc.ogc-utils.prov
+  - type: object
+    required:
+      - id
+      - processType
+      - used
+      - generated
+    properties:
+
+      id:
+        description: Stable identifier for this processing step activity.
+        type: string
+
+      processType:
+        description: >-
+          Identifier of the registered process type this step is an instance
+          of. This is the link that PROV-O and OGC API - Processes Part 5 do
+          not themselves provide.
+        type: string
+
+      label:
+        type: string
+
+      startedAtTime:
+        type: string
+        format: date-time
+
+      endedAtTime:
+        type: string
+        format: date-time
+
+      used:
+        description: Entities consumed by this step.
+        type: array
+        minItems: 1
+        items:
+          type: string
+
+      generated:
+        description: Entities produced by this step.
+        type: array
+        minItems: 1
+        items:
+          type: string
+
+      qualifiedUsage:
+        description: >-
+          Which declared input slot of the process type each consumed entity
+          occupied. Makes two runs of the same process type comparable.
+        type: array
+        items:
+          type: object
+          required:
+            - entity
+            - hadRole
+          properties:
+            entity:
+              type: string
+            hadRole:
+              type: string
+
+      wasAssociatedWith:
+        type: array
+        items:
+          type: string
+
+      parameters:
+        description: >-
+          Parameter values that determined the behaviour of this step. Keys
+          SHOULD be drawn from the parameter terms declared by the registered
+          process type.
+        type: object
+        additionalProperties: true

bblocks-config.yaml

@@ -18,6 +18,7 @@ imports:
   - https://ogcincubator.github.io/bblocks-ogcapi-processes
   - https://ogcincubator.github.io/prov-cwl/
   - https://ogcincubator.github.io/bblocks-wf4ever/
+  - https://ogcincubator.github.io/bblock-prov-schema/
   - https://ogcincubator.github.io/bblocks-stac
   - https://ogcincubator.github.io/cross-domain-model
 

build-devel.sh

@@ -0,0 +1,3 @@
+#!/bin/bash
+# Process building blocks using the development (rolling) image build
+BBP_IMAGE_TAG=develop exec "$(dirname "$0")/build.sh" "$@"

build.sh

@@ -9,7 +9,7 @@ if [ -f '.volumes' ]; then
     fi
   done < .volumes)
 fi
-docker run --pull=always --rm --workdir /workspace -v "$(pwd):/workspace" ${VOLUMES} \
+docker run -it --pull=always --rm --workdir /workspace -v "$(pwd):/workspace" ${VOLUMES} \
   ghcr.io/opengeospatial/bblocks-postprocess \
   --clean true --base-url http://localhost:9090/register/
 

create-clean-pr.sh

@@ -0,0 +1,148 @@
+#!/usr/bin/env bash
+# Creates a "clean" branch of a Building Blocks register fork, excluding all
+# changes in the build/ directory (and fork-only config overrides), so that
+# it can be used to open a Pull Request against the upstream register without
+# generated-artifact merge conflicts.
+#
+# See https://opengeospatial.github.io/bblocks-docs/build/contribution for details.
+
+usage() {
+  echo "Usage: $0 [-u upstreamRemote] [-f forkRemote] [-b upstreamBranch] [-d buildDirectory] [-t tempBranch] [-P]"
+  echo
+  echo "Options:"
+  echo "  -u    Upstream remote name (default: 'fork-parent')"
+  echo "  -f    Fork remote name (default: 'origin')"
+  echo "  -b    Upstream branch (default: 'main' or 'master')"
+  echo "  -d    Build directory (default: 'build')"
+  echo "  -t    Name for the temporary clean branch (default: randomly generated)"
+  echo "  -P    Do not push to remote"
+  echo "  -h    Show this help message"
+  exit 1
+}
+
+UPSTREAM_REMOTE=fork-parent
+BUILD_DIR=build
+FORK_REMOTE=origin
+UPSTREAM_BRANCH=
+PUSH_TO_REMOTE=1
+TMP_BRANCH=
+
+while getopts "u:f:b:d:t:Ph" opt; do
+  case $opt in
+    u) UPSTREAM_REMOTE="$OPTARG" ;;
+    f) FORK_REMOTE="$OPTARG" ;;
+    b) UPSTREAM_BRANCH="$OPTARG" ;;
+    d) BUILD_DIR="$OPTARG" ;;
+    P) PUSH_TO_REMOTE=;;
+    t) TMP_BRANCH="$OPTARG";;
+    h) usage ;;
+    \?) usage ;;
+  esac
+done
+
+trap_add() {
+    local cmd="$1"
+    # shellcheck disable=SC2064
+    trap "${cmd};$(trap -p EXIT | cut -d"'" -f2)" EXIT
+}
+
+if ! git rev-parse --is-inside-work-tree >/dev/null 2>&1; then
+    echo "This script must be run inside a git directory."
+    echo "If you are using Docker, check you have mounted the right volumes."
+    exit 1
+fi
+
+if ! ( git diff --quiet && git diff --cached --quiet ); then
+  echo "There are pending changes. Please commit or stash them before continuing."
+  exit 1
+fi
+
+# Detect git-filter-repo
+if [[ -x "./git-filter-repo" ]]; then
+    FILTER_REPO_CMD="./git-filter-repo"
+elif command -v git-filter-repo >/dev/null 2>&1; then
+    FILTER_REPO_CMD="git-filter-repo"
+elif git filter-repo --help >/dev/null 2>&1; then
+    FILTER_REPO_CMD="git filter-repo"
+else
+    # Download the latest released version to a temp location
+    LATEST_TAG=$(curl -sSfL https://api.github.com/repos/newren/git-filter-repo/releases/latest \
+        | sed -n 's/.*"tag_name": *"\([^"]*\)".*/\1/p')
+    if [[ -z "$LATEST_TAG" ]]; then
+        echo "Could not determine the latest git-filter-repo release." >&2
+        exit 1
+    fi
+    TMP_DIR=$(mktemp -d)
+    FILTER_REPO_CMD="$TMP_DIR/git-filter-repo"
+    if ! curl -sSfL -o "$FILTER_REPO_CMD" \
+        "https://raw.githubusercontent.com/newren/git-filter-repo/${LATEST_TAG}/git-filter-repo"; then
+      echo "Failed to download git-filter-repo ${LATEST_TAG}." >&2
+      rm -rf "$TMP_DIR"
+      exit 1
+    fi
+    chmod +x "$FILTER_REPO_CMD"
+    trap_add "rm -rf \"$TMP_DIR\""
+fi
+echo "Using git-filter-repo command: $FILTER_REPO_CMD"
+
+CURRENT_BRANCH=$(git rev-parse --abbrev-ref HEAD)
+trap_add "git checkout \"$CURRENT_BRANCH\" >/dev/null 2>/dev/null"
+
+UPSTREAM_URL=$(git remote get-url "$UPSTREAM_REMOTE" 2>/dev/null)
+if [[ $? -ne 0 || -z "$UPSTREAM_URL" ]]; then
+  echo "Upstream remote '$UPSTREAM_REMOTE' does not exist. Please add it first by running:"
+  echo "  git remote add ${UPSTREAM_REMOTE} git@github.com:username/repo.git"
+  exit 1
+fi
+echo "Using upstream remote: ${UPSTREAM_REMOTE} / ${UPSTREAM_URL}"
+
+FORK_URL=$(git remote get-url "$FORK_REMOTE" 2>/dev/null)
+if [[ $? -ne 0 || -z "$FORK_URL" ]]; then
+  echo "Fork (local) remote '$FORK_REMOTE' does not exist."
+  exit 1
+fi
+echo "Using fork remote: ${FORK_REMOTE} / ${FORK_URL}"
+
+set -euo pipefail
+git fetch "${UPSTREAM_REMOTE}"
+
+if [[ -z "$TMP_BRANCH" ]]; then
+  TMP_BRANCH="clean-pr-$(date +%s).$RANDOM"
+fi
+git checkout -b "$TMP_BRANCH"
+
+if [[ -z "${UPSTREAM_BRANCH}" ]]; then
+  if git rev-parse --verify --quiet "${UPSTREAM_REMOTE}"/main >/dev/null; then
+    UPSTREAM_BRANCH=main
+  else
+    UPSTREAM_BRANCH=master
+  fi
+fi
+echo "Using upstream branch: ${UPSTREAM_BRANCH}"
+
+$FILTER_REPO_CMD --path "${BUILD_DIR}" --path .fork --path bblocks-config-override.yml --path bblocks-config-override.yaml --invert-paths --force \
+  --refs "${UPSTREAM_REMOTE}/${UPSTREAM_BRANCH}..HEAD"
+
+if [[ -n "$PUSH_TO_REMOTE" ]]; then
+  git push "${FORK_REMOTE}" "${TMP_BRANCH}"
+  echo "Branch created and changed pushed"
+
+  # Strip a trailing .git suffix, then split "owner/repo" on the last slash/colon.
+  UPSTREAM_PATH="${UPSTREAM_URL#git@github.com:}"
+  UPSTREAM_PATH="${UPSTREAM_PATH#https://github.com/}"
+  UPSTREAM_PATH="${UPSTREAM_PATH%.git}"
+
+  FORK_PATH="${FORK_URL#git@github.com:}"
+  FORK_PATH="${FORK_PATH#https://github.com/}"
+  FORK_PATH="${FORK_PATH%.git}"
+
+  PR_URL="https://github.com/${UPSTREAM_PATH}/compare/${UPSTREAM_BRANCH}...${FORK_PATH%%/*}:${FORK_PATH#*/}:${TMP_BRANCH}?expand=1"
+  echo ""
+  echo "========"
+  echo "You can use the following URL to create the Pull Request:"
+  echo "  ${PR_URL}"
+  echo "========"
+  echo ""
+else
+  echo "Branch '${TMP_BRANCH}' created - push disabled"
+fi